M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionOpenNutrition MCP ServerAccess the OpenNutrition food database with 300,000+ itemsMCP Toolbox for DatabasesGoogle's official database MCP toolbox — define AI-accessible database tools via config
FMRS33 / 100 · D74 / 100 · B
Reliability6 / 2013 / 20
Security and permissions6 / 2013 / 20
Maintenance8 / 2017 / 20
Documentation7 / 2016 / 20
Setup experience6 / 2015 / 20
Best for
  • Developers requiring reliable nutritional data
  • Researchers
  • Health app developers
  • Teams that want precise control over which database operations an AI can perform, rather than open arbitrary SQL execution
  • Scenarios needing a unified MCP setup across multiple database engines
Not for
  • Those needing real-time web data
  • Those needing user-generated content databases
  • Lightweight cases that just want to run a few ad-hoc SQL queries without maintaining a tools.yaml config (a simpler single-database MCP may be a better fit)
Required permissions
  • Local file access (possible)
  • Network access (for dataset download, but no external calls at runtime)
  • Database credentials (username/password/connection string) are supplied via env vars or config
  • A tool's actual permission is whatever SQL statement is defined in tools.yaml — designed for least privilege, but misconfiguration can still over-expose access
Risks and side effects
  • Local data storage may consume space
  • Risk of outdated data
  • If tools.yaml defines SQL statements that allow unconstrained writes or deletes, the AI could accidentally modify data
  • The prebuilt toolsets (--prebuilt) favor convenience and may expose broader query capability than a specific business actually needs — use a custom tools.yaml in production
Supported clientsClaudeClaude Code, Gemini CLI, Zed, Antigravity
Tools40